Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), so the bar is lower; the description adds genuine behavior beyond them by stating the coverage-fallback rule ('if the night was not sampled, returns the nearest checked nights') and that figures are aggregate/typical rather than a single property. It stops short of describing the response shape, but that is a minor gap given the safety fields are already declared.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, with the substantive outputs listed up front and the fallback rule placed as a closing caveat where it belongs. The 'what is on' clause is slightly loose but does not cost the definition anything structurally.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining returns, and it does so by listing price, baseline comparison, sell-out counts, events, and the points/cash verdict. A single-parameter, read-only tool is well covered; only the exact response shape and any date-range limits remain unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter already documents the YYYY-MM-DD format, so the baseline would be 3. The description adds real meaning beyond the schema by explaining what happens when the supplied date has no sample (nearest checked nights are returned), which directly affects how the agent should interpret the date argument and its result.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (typical Miami Beach/Brickell hotel cost for a given night) and enumerates the returns: price vs. a quiet midweek baseline, sold-out counts, events on, and a points-vs-cash signal. That is concrete enough to distinguish it from siblings like best_nights or whats_on, though it is framed as a data list rather than an explicit verb+resource statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the 'points or cash' clause and the baseline comparison suggest a decision-support use case for a specific night. There is no explicit when-to-use/when-not-to-use guidance and no routing to overlapping siblings such as best_nights or whats_on, so the agent must infer selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.